Canva is diving deeper into AI with the launch of an image generation model that directly competes with those from OpenAI, Microsoft and Google. The model, called Canva Craft, uses a two-stage architecture that allows you to plan a design before generating an image, allowing for “greater precision, consistency and control,” according to a Thursday announcement.
Canva Craft can generate images up to 2K resolution and in over 30 aspect ratios. Apart from generating social media posts and marketing content, you are also supposed to create realistic scenes, digital art, environmental images, and more. According to Canva, the model’s two-stage system allows it to more accurately generate complex images that require readable text and precise object placement.
Canva says it trained Craft on “millions of human-created templates” from the platform’s content library, which includes things like social media posts, presentations, infographics and menus. The model is currently ranked fourth on Design Arena’s leaderboard for best AI imaging models, a crowdsourced benchmark for AI designs. It sits behind GPT-Image-2.5 Sunburst, GPT-Image-2.5 Flare, and OpenAI’s GPT-Image-2.
Canva notes that its AI model comes with “robust input and output moderation, privacy and security controls, and reporting tools.” The company plans to allow AI agents to connect to Canva Craft through the open model context protocol, and will also implement more efficient Craft-fast and Craft-ultrafast models in the future.
Canva Craft is now available to all users worldwide. You can try it out by navigating to the three dots option in Canva’s left menu and then selecting Dream Lab.
